Mipu

Predictive Hub

Manufacturing

MACHINE PERFORMANCE OPTIMIZATION IN THE PACKAGING SECTOR

by

Monitoring equipment and optimising after sales activities

Machine manufacturers must always be able to ensure the performances of their machines and provide efficient after sales services.  In order to do it, they can use Industry 4.0 solutions like Internet of Things, Artificial Intelligence and Data Analytics.

MIPU supported one of these companies in the machinery sector providing a software platform for performance monitoring and maintenance management.

 

THE CUSTOMER

The client is a company located near Bergamo that has a decade of experience in the design and production of conifying machines. Its experience in the field have made the company the perfect partner for companies in the packaging sector.

 

CUSTOMER NEEDS

The main need of the customer was a software platform able to provide the overview of the machines distributed worldwide. Furthermore, the client wanted to offer after-sales services such as ticket management, failure prediction and energy consumption monitoring.

Lastly, the platform needed to be integrable with the classic SCADA already in use by the customer for the visualization and management of activities, but only at a local level.

THE CHOICE OF MIPU

The client chose MIPU as a partner in this challenge because we are able to provide a single platform for all these needs. In fact, our platform Rebecca sums up Internet of Things, asset management, consumption monitoring and creation of codeless Artificial Intelligence models. Furthermore, Rebecca is integrable with other systems without difficult configurations.

 

MIPU SOLUTION

MIPU, first of all, installed a remote acquisition software on the operator panel of the machine. This software communicates with the conifying machine and receives the information that are sent with a fixed frequency to Rebecca, on the cloud of the company. These information are of three types: general data about the machine, specific data about pliers and other components, recipe data about the processed product.

 

 

Every conifying machine represents an asset on the platform and general data are collected for each of them. Through a dedicated dashboard, the company and its customers can visualize analysis of production, waste, analysis of OEE and machine downtimes.

 

 

Furthermore, a specific dashboard was created in order to gather the data about the 36 pliers that work on the jars and the other components.

 

 

The platform has also a Ticket application for the opening of assistance tickets related to the machine. With this application, the end clients are able to communicate anomalies to the company right away and receive a rapid remote intervention. Furthermore, the platform is complemented by an energy application for the energy consumption monitoring of each conifying machine.

The offered solution is completed by Artificial Intelligence models for the diagnosis of the conifying machine. The models are already built in: users just choose the preferred analysis that the AI must perform and connect to the machines data for the training of the models.

 

RESULTS

Thanks to the implemented solution, the company now is able to:

  • • Offer to its customer worldwide a complete platform for machine performance analysis and energy consumption monitoring;
  • • Supply to the customers an efficient and quick after-sales service through the use of tickets;
  • • Identify and predict possible causes of failure through the use of artificial intelligence models.

 

CONCLUSIONS

Starting from the specific needs of the customer, MIPU offered a software solution with a personalized Data Experience able to adapt to the specific characteristics of each machine and easy to integrate with other software platforms already in use.

Rebecca Machinery is our software solution created specifically for machine manufacturers, in order to empower their assets through their entire life cycle, from design to after-sales.

If you want to know more about it, contact us to know more!

REDUCE THE ENERGY CONSUMPTION OF A PRODUCTION LINE

by

The following case study reports a project of Energy Efficiency in production plants, implemented in the manufacturing sector. In just one year, MIPU has managed to reduce the energy consumption of a customer’s production line by 11%.

“We didn’t expect there was so much energy waste in our process. This project has given us a great competitive advantage” – Technical Director.

“With better performance reports it is easier to inform the Board and get the approval for efficiency activities” – Chief Production Manager.

Energy efficiency is a key element in the journey towards a sustainable energy future. As the global energy demand continues to grow, actions aimed at increasing the energy efficiency are essential.

It is fundamental to improve the energy efficiency of plants in the industrial sector. This is because “energy efficiency” does not imply producing less to reduce energy consumption. Rather, it allows to enhance the plant productivity and efficiency, permitting the plant to produce the same with less resources.

Therefore, in industry more than elsewhere, energy efficiency has heavy implications both on the profitability and on the sustainability of production.

Process automation can help to improve the energy efficiency of industrial production plants in many ways. Implementing monitoring, control and optimization strategies positively affects energy performance. Directly, reducing waste, and indirectly, through maintenance practices that help to prevent an increase in energy consumption due to downtime, stop and start processes as well as defective products.

 

CUSTOMER PROFILE

In this case study, our client is a large company specialized in the production of metal components. It is also a world leader in the production of wagon parts, offering the widest choice of components and track-laying systems for tracked machines. Its production centers provide components and tracks for the main OEMs earthmoving machines, including Caterpillar, Komatsu, Hitachi, John Deere, Liebherr, Case CE and Dresserr.

 

CUSTOMER’S NEEDS: REDUCE ENRGY CONSUMPTION

The Ferrara plant covers almost 600.000 sm. and hosts 2.300 employees working with a three-shifts system. Every year the company spends about EUR 30 million on electricity and gas. Over the last 10 years, the Board has invested more than EUR 400 million in Innovation. Ferrara has used part of these investments to optimize energy use and become more efficient. The client contacted MIPU with the intention of starting a pilot project in order to assess the potential savings on the Ferrara site. The challenge was to reduce energy consumption of a production line by 5% with only 4 measuring devices and one-year ROI limit.

 

OUR SOLUTION FOR THE ENERGY CONTROL OF A PRODUCTION LINE

As first step, MIPU analyzed the whole production line and defined the most critical area, with the purpose of reducing initial investments and obtaining rapid and measurable results. This has become the goal of the pilot project. The critical production area identified was a molding line, composed of cutting bars plus load bars, oven, press and deburring machine. The annual expenditure on electricity was €400.000, which represented approximately 5% of the total expenditure on electricity of the plant.

RIDURRE IL CONSUMO ENERGETICO DI UNA LINEA DI PRODUZIONE

Consumption exceeds normal values due to a mechanical failure

Having 13 months of data collection, thanks to the 4 existing measuring devices, MIPU collected additional production data and started modeling the energy consumption of the line. This approach has made it possible to understand and predict the consumption of each component. Through historical data, it was therefore possible to identify causes of energy waste and inefficiency and thus set up an automated control of energy consumption.

 

THE RESULTS ACHIEVED: REDUCED BY 11% THE ENERGY CONSUMPTION OF A PRODUCTION LINE

Once consumption and costs were predicted, our costumer used CUSUM control charts to control consumption on an ongoing basis. As a result it was possible to:

  • – Understand the effects of interventions from an energy point of view;
  • – Find previous defects and define procedures to avoid them for an estimate return of €20.000/year;
  • – Use our software platform to automatically monitor the consumption of the production line avoiding additional waste with the value of €10.000/ year. An example of waste avoided is the detection of line malfunctioning;
  • – Improve maintenance by simply monitoring energy consumption. This resulted in additional direct cost savings of €5.000/year;
  • – Optimize the set-up parameters of the equipment, such as the oven temperature, the production cycle, guaranteeing an additional saving of 10,000 € / year;
  • – Know, verify and monitor the return on each action of energy efficiency;
  • – Plan a consumption budget for the line equipment;

Now the company is working on the third and fourth phase of the project: load management and continuous improvement.
In the load management phase, the Energy Manager is considering the possibility of reducing or dividing the use of the equipment into different tariff periods. Furthermore, The Energy Manager is setting up an automatic system to adjust HVAC operating parameters and illumination for different seasons.

The final energy saving was €45.000 for one year, meaning that thanks to this project the customer reduced by 11% the energetic consumption of the production line. This convinced the producer to install other 16 measuring devices in order to cover 80% of the total consumption. In this way, they were able to distribute the results obtained so far to the rest of their plant.

If you want to discuss a possible pilot project for your production site, just contact us.

PREDICT FAILURES WITH MACHINE LEARNING: REAL CASE STUDIES

by

The following case study reports the methods used and the results achieved by MIPU with a project whose objective was to avoid faults through the application of Machine Learning. The project has been developed for a client company working in the manufacturing industry.

PREVENT FAILURES WITH MACHINE LEARNING: THE PATH

Machine Learning applications for Predictive Maintenance are used to identify the occurrence of a failure, before this happens. Those who are familiar with the P-F Curve know that the quicker you identify a potential defect, the sooner you avoid machine downtime.

  • – The first step of a Machine Learning analysis process requires the creation of an asset’s mathematical model. This model includes all the process parameters associated with that specific asset. These parameters normally are stored in a database, which acquires data from plant DCS, associated PLCs, electronic registers etc…
    For instance, if you’re designing a pump model, things as suction and discharge pressure, control valve position, bearing temperature and vibration are some good examples of parameters to include in the model. Most of the models have between 10 and 30 parameters, but there are models that have almost 100 parameters.

 

  • – As second step, parameters historical data are imported into the model. This dataset is generally known as “training” data set and it normally includes a year of data. One-year dataset allows the model to take into consideration the seasonal variations of management operations. An expert in asset functioning knows which data are to be included or excluded within the training set, because he/she has specific competences in this field: a strong domain knowledge.

 

  • – During the third step, the training dataset is used to develop an asset operational matrix. This matrix identifies how the machine should work in a precise moment, on the basis of the training data used to create it.

 

  • – In the last step, the software constantly monitors the machine operations and predicts the values of the machine parameters according to the matrix that has received as input. If a parameter deviates from the prediction of the model with a significant percentage, the system creates an alert related to that specific parameter. Then, a technical analysis is executed on the asset in order to evaluate the change of condition and the reasons that might have caused it.
    (Can your software do it? If not, you may want to upgrade it)

 

PREVENT FAILURES WITH MACHINE LEARNING: APPLICATIONS

CASE 1

Picture number 1 shows a bearing vibrational increment of a ventilator fan, caused by an oil leak. This condition generated an alarm. The solution created using Machine Learning predicted a bearing vibration of about 3,5mm, given the operating conditions. The bearing vibration slowly deviated from the predicted value, creating an alarm as soon as it reached the value of 4,7mm.
Thus, the plant technical managers were alerted and through fan visual inspection they identified an oil leak. The ventilator vacuum was actually vacuuming up the oil spilled from the leak in the fan lodging. For this reason, there was no leak sign on the ground. The oil on fan blades accumulated dirt and debris, causing a rotation imbalance and consequently a vibration increment. The plant technical managers were able to take corrective actions to stop the leak before the bearing was damaged.
.

Predict failures with machine learning
Increase of Fan Vibration

CASE 2

Picture number 2 concerns the lubrication system of a big pulverizer. The lubrication system provides oil to the gearbox and to all the bearings. The asset model predicted a temperature of 90° F, but the real temperature reached 110° F. Therefore, the software generated an alarm for the plant technicians, who discovered that the control valve of the cooling water of the heat exchanger was not functioning. The control valve was replaced and the system started working again.

Predict failures with machine learning
Pulverizer Oil Temperature

CASE 3

Picture number 3 is about an electro-hydraulic control (EHC) system that verifies the valve position, turbine velocity and security valves. In this case, the differential pressure through the EHC pump “A” filter began to increase. Technicians were alarmed in time and they were able to switch from pump “A” to pump“B”. In this way, it was possible to avoid the emergency shutdown of the turbine and all the connected damages.

Predict failures with machine learning
Electro-hydraulic System Filter

To know more about this case study or to learn how to create machine learning models for your assets, contact us!